“Today on Connectionism: how we trained Inkling 2 Small with a native 4-bit forward…”
Mira Murati @miramuratiX
Archived text
Today on Connectionism: how we trained Inkling 2 Small with a native 4-bit forward pass on @nvidia GB300s, from the first pretraining step through the final RL rollout, one of the many improvements across the stack that took pretraining from weeks to 68 hours.
Quoting @thinkymachines: Training with fewer bits is faster, but quantization error can interfere with learning.
Today on Connectionism, we detail how we trained Inkling 2 Small with a native 4-bit forward pass from the first step of pretraining through the final RL rollout. https://thinkingmachines.ai/blog/end-to-end-4-bit-training